The University of Southampton
University of Southampton Institutional Repository

Monostable controllers for adaptive behavior

Monostable controllers for adaptive behavior
Monostable controllers for adaptive behavior
Recent artificial neural networks for machine learning have exploited transient dynamics around globally stable attractors, inspired by the properties of cortical microcolumns. Here we explore whether similarly constrained neural network controllers can be exploited for embodied, situated adaptive behaviour. We demonstrate that it is possible to evolve globally stable neurocontrollers containing a single basin of attraction, which nevertheless sustain multiple modes of behaviour. This is achieved by exploiting interaction between environmental input and transient dynamics. We present results that suggest that this globally stable regime may constitute an evolvable and dynamically rich subset of recurrent neural network configurations, especially in larger networks. We discuss the issue of scalability and the possibility that there may be alternative adaptive behaviour tasks that are more ‘attractor hungry’.
Global stability, echo state networks, evolvability
103-112
Springer
Buckley, C. L.
403be04e-fca5-4f1c-b0c4-d84401f51d51
Fine, Peter
a481144f-f479-48e8-ba61-4fc6f8031744
Bullock, Seth
2ad576e4-56b8-4f31-84e0-51bd0b7a1cd3
Di Paolo, Ezequiel
51ffe663-860e-46bd-ad42-1e9fd76a155e
Asada, M.
Hallam, J. C. T.
Meyer, J.-A.
Tani, J.
Buckley, C. L.
403be04e-fca5-4f1c-b0c4-d84401f51d51
Fine, Peter
a481144f-f479-48e8-ba61-4fc6f8031744
Bullock, Seth
2ad576e4-56b8-4f31-84e0-51bd0b7a1cd3
Di Paolo, Ezequiel
51ffe663-860e-46bd-ad42-1e9fd76a155e
Asada, M.
Hallam, J. C. T.
Meyer, J.-A.
Tani, J.

Buckley, C. L., Fine, Peter, Bullock, Seth and Di Paolo, Ezequiel (2008) Monostable controllers for adaptive behavior. Asada, M., Hallam, J. C. T., Meyer, J.-A. and Tani, J. (eds.) In From Animals to Animats 10: Proceedings of the Tenth International Conference on Simulation of Adaptive Behavior. Springer. pp. 103-112 .

Record type: Conference or Workshop Item (Paper)

Abstract

Recent artificial neural networks for machine learning have exploited transient dynamics around globally stable attractors, inspired by the properties of cortical microcolumns. Here we explore whether similarly constrained neural network controllers can be exploited for embodied, situated adaptive behaviour. We demonstrate that it is possible to evolve globally stable neurocontrollers containing a single basin of attraction, which nevertheless sustain multiple modes of behaviour. This is achieved by exploiting interaction between environmental input and transient dynamics. We present results that suggest that this globally stable regime may constitute an evolvable and dynamically rich subset of recurrent neural network configurations, especially in larger networks. We discuss the issue of scalability and the possibility that there may be alternative adaptive behaviour tasks that are more ‘attractor hungry’.

PDF
BuckleyFineBullockDiPaolo2008.pdf - Other
Download (392kB)

More information

Published date: 2008
Keywords: Global stability, echo state networks, evolvability
Organisations: Agents, Interactions & Complexity

Identifiers

Local EPrints ID: 266775
URI: https://eprints.soton.ac.uk/id/eprint/266775
PURE UUID: 857d805f-06a0-4284-a475-421f05e36f51

Catalogue record

Date deposited: 12 Oct 2008 13:55
Last modified: 18 Jul 2017 07:12

Export record

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of https://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×